Gate Square “Creator Certification Incentive Program” — Recruiting Outstanding Creators!
Join now, share quality content, and compete for over $10,000 in monthly rewards.
How to Apply:
1️⃣ Open the App → Tap [Square] at the bottom → Click your [avatar] in the top right.
2️⃣ Tap [Get Certified], submit your application, and wait for approval.
Apply Now: https://www.gate.com/questionnaire/7159
Token rewards, exclusive Gate merch, and traffic exposure await you!
Details: https://www.gate.com/announcements/article/47889
DeepChao TechFlow News, January 21, according to Jin10 Data, on the first anniversary of the release of DeepSeek-R1, the new model “MODEL1” was revealed. DeepSeek updated the FlashMLA code on GitHub, with 28 mentions of MODEL1 across 114 files, appearing alongside V32 as a different model. It is known that V32 is DeepSeek-V3.2, and MODEL1 is very likely a new architecture. The specific differences in the code are reflected in the KV cache layout, sparsity handling, and FP8 decoding, with multiple variations in memory optimization. (Quantum bit)